Torch Implementation of NIPS'16 paper: Perspective Transformer Nets
This is the code for NIPS 2016 paper Perspective Transformer Nets: Learning Single-View 3D Object Reconstruction without 3D Supervision by Xinchen Yan, Jimei Yang, Ersin Yumer, Yijie Guo and Honglak Lee
Please follow the instructions to run the code.
PTN requires or works with
The following command installs the Perspective Transformer Layer:
./install_ptnbhwd.sh
./prepare_data.sh
PTN-Proj: ptn_proj.t7
PTN-Comb: ptn_comb.t7
CNN-Vol: cnn_vol.t7
./download_models.sh
./eval_models.sh
./demo_pretrain_singleclass.sh
./demo_train_ptn_proj_singleclass.sh
./demo_train_ptn_comb_singleclass.sh
./demo_train_cnn_vol_singleclass.sh
In many cases, you want to implement your own camera matrix (e.g., intrinsic or extrinsic). Please feel free to modify this function.
Before start your own implementation, we recommand to go through some basic camera geometry in this computer vision textbook written by Richard Szeliski (see Eq 2.59 at Page 53).
Note that in our voxel ray-tracing implementation, we used the inverse camera matrix.
Besides our torch implementation, we recommend to see also the following third-party re-implementation:
If you find this useful, please cite our work as follows:
@incollection{NIPS2016_6206,
title = {Perspective Transformer Nets: Learning Single-View 3D Object Reconstruction without 3D Supervision},
author = {Yan, Xinchen and Yang, Jimei and Yumer, Ersin and Guo, Yijie and Lee, Honglak},
booktitle = {Advances in Neural Information Processing Systems 29},
editor = {D. D. Lee and M. Sugiyama and U. V. Luxburg and I. Guyon and R. Garnett},
pages = {1696--1704},
year = {2016},
publisher = {Curran Associates, Inc.},
url = {http://papers.nips.cc/paper/6206-perspective-transformer-nets-learning-single-view-3d-object-reconstruction-without-3d-supervision.pdf}
}